Files
netbird/shared/relay/client/fallback_opener.go
Zoltan Papp cf101c44b4 [relay] Count winning attempt before draining losers
The success path in handleResult left settled at 0, so drainLoser
waited on a result that was already consumed and blocked forever,
leaking a goroutine and the results channel on every successful race.
Increment settled before stop() so drainLoser only waits for actual
started losers.
2026-07-02 12:22:01 +02:00

166 lines
3.7 KiB
Go

package client
import (
"context"
"errors"
"net"
"time"
log "github.com/sirupsen/logrus"
)
const (
raceTotalTimeout = 40 * time.Second
raceFallbackDelay = 10 * time.Second
)
type raceAttempt struct {
conn net.Conn
err error
}
type raceOutcome struct {
conn net.Conn
err error
done bool
}
type connRace struct {
opener *FallbackOpener
peerKey string
remoteRelayServer RelayServer
preferForeign bool
raceCtx context.Context
otherCtx context.Context
cancelPreferred context.CancelFunc
cancelOther context.CancelFunc
results chan raceAttempt
fallbackTimer *time.Timer
otherStarted bool
settled int
lastErr error
}
type FallbackOpener struct {
home *Client
foreignStore *ForeignRelaysStore
}
func NewFallbackOpener(home *Client, foreignStore *ForeignRelaysStore) *FallbackOpener {
return &FallbackOpener{
home: home,
foreignStore: foreignStore,
}
}
func (r *FallbackOpener) Run(ctx context.Context, peerKey string, remoteRelayServer RelayServer, preferForeign bool) (net.Conn, error) {
raceCtx, cancel := context.WithTimeout(ctx, raceTotalTimeout)
defer cancel()
preferredCtx, cancelPreferred := context.WithCancel(raceCtx)
otherCtx, cancelOther := context.WithCancel(raceCtx)
race := &connRace{
opener: r,
peerKey: peerKey,
remoteRelayServer: remoteRelayServer,
preferForeign: preferForeign,
raceCtx: raceCtx,
otherCtx: otherCtx,
cancelPreferred: cancelPreferred,
cancelOther: cancelOther,
results: make(chan raceAttempt, 2),
fallbackTimer: time.NewTimer(raceFallbackDelay),
}
defer race.fallbackTimer.Stop()
go func() {
race.results <- r.open(preferredCtx, peerKey, remoteRelayServer, preferForeign)
}()
for {
select {
case <-race.fallbackTimer.C:
race.startOther()
case res := <-race.results:
if o := race.handleResult(res); o.done {
return o.conn, o.err
}
case <-raceCtx.Done():
return race.onTimeout()
}
}
}
func (c *connRace) startOther() {
if c.otherStarted {
return
}
c.otherStarted = true
c.fallbackTimer.Stop()
go func() {
c.results <- c.opener.open(c.otherCtx, c.peerKey, c.remoteRelayServer, !c.preferForeign)
}()
}
func (c *connRace) handleResult(res raceAttempt) raceOutcome {
if (res.err == nil && res.conn != nil) || errors.Is(res.err, ErrConnAlreadyExists) {
c.settled++
c.stop()
return raceOutcome{conn: res.conn, err: res.err, done: true}
}
c.lastErr = res.err
c.settled++
if !c.otherStarted {
c.startOther()
return raceOutcome{}
}
if c.settled == 2 {
c.cancelPreferred()
c.cancelOther()
return raceOutcome{err: c.lastErr, done: true}
}
return raceOutcome{}
}
func (c *connRace) onTimeout() (net.Conn, error) {
c.stop()
if c.lastErr != nil {
return nil, c.lastErr
}
return nil, c.raceCtx.Err()
}
func (c *connRace) stop() {
c.cancelPreferred()
c.cancelOther()
go c.opener.drainLoser(c.results, c.settled, c.otherStarted)
}
func (r *FallbackOpener) open(ctx context.Context, peerKey string, remoteRelayServer RelayServer, foreign bool) raceAttempt {
if foreign {
conn, err := r.foreignStore.OpenConn(ctx, peerKey, remoteRelayServer)
return raceAttempt{conn: conn, err: err}
}
conn, err := r.home.OpenConn(ctx, peerKey)
return raceAttempt{conn: conn, err: err}
}
func (r *FallbackOpener) drainLoser(results chan raceAttempt, settled int, otherStarted bool) {
started := 1
if otherStarted {
started = 2
}
for i := settled; i < started; i++ {
res := <-results
if res.conn != nil {
if err := res.conn.Close(); err != nil {
log.Debugf("failed to close losing relay connection: %v", err)
}
}
}
}